Automated detection of citrus trees from a digital surface model

Abstract

In this paper, we present an approach to detect citrus trees from digitals surface models (DSMs) generated from Unmanned Aerial Vehicle (UAV). The symmetric characteristics of the citrus trees in a DSM are revealed by orientation-based radial symmetry transform. The method is tested on four UAV DSMs that have different planting characteristics of citrus orchards. The approach is compared with three previously developed approaches. Comparison to the state-of-the-art reveals that the proposed approach provides superior detection performances through supporting a nice balance between precision and recall measures.